Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MartinPuli/createAnApp --skill ios-release-testergit clone --depth 1 https://github.com/MartinPuli/createAnAppWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/martinpuli/createanapp/ios-release-tester)<a href="https://agentmods.dev/skills/martinpuli/createanapp/ios-release-tester"><img src="https://agentmods.dev/badge/skills/martinpuli/createanapp/ios-release-tester.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.00747 |
| Opus 5 | $0.00036 | $0.00374 |
| Sonnet 5 | $0.00015 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
ios-release-tester scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS Release Tester
Test the commercial and operational lifecycle of the exact release candidate. A clean compile is only the first row of evidence.
Identify the candidate
Record commit, marketing version, build number, scheme/configuration, bundle ID, archive path, Xcode/SDK, supported devices, minimum OS, StoreKit product IDs, and metadata revision. Confirm Xcode/SDK eligibility against ../../docs/current-apple-requirements.md. Run scripts/inspect_xcode_project.sh <project-root> for a sanitized first pass.
Build the matrix
Cover:
- clean build and complete automated suite;
- smallest/largest supported devices and every declared family;
- orientations and iPad multitasking/window widths if supported;
- current release OS plus minimum supported OS where feasible;
- clean install, upgrade/migration, termination/relaunch, offline, storage/error recovery;
- core journeys, destructive actions, imports/exports, sharing, permissions, support/legal links;
- VoiceOver, Dynamic Type, contrast, focus, keyboard/pointer/Pencil where promised;
- privacy manifest, entitlements, SDK/network inventory, and permission strings;
- release archive, signing, export validation, upload processing, TestFlight installation.
- account creation/deletion, third-party login, UGC moderation, and regulated workflows when present.
Test StoreKit as a state machine
Layer evidence:
- Local StoreKit configuration: deterministic product/purchase/refund/expiration tests.
- Sandbox or TestFlight: real configured products and Apple account flow.
- App relaunch/offline: entitlement reconstruction and cache limits.
- Transaction change: renewal, cancellation at period end, billing retry/grace if used, refund/revocation, upgrade/downgrade.
- Restore: fresh install/device where feasible and clear no-purchase behavior.
Verify product identifiers, localized price/period, entitlement mapping, legal copy, close path, and access to paid value. Do not call local StoreKit proof “TestFlight tested.”
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 60 lines · 73 tokens per session scan A bccd69f88789
ios-release-tester is a skill published in the GitHub repository MartinPuli/createAnApp (14 stars, last pushed 18d ago), licensed MIT. It adds 73 tokens to every session and 747 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ui-crawler-max
Autonomous UI crawler for iOS simulator apps — rapid, element-precise data collection. Use whenever the user says "crawl my app", "auto-test the UI", "click/tap through every screen", "monkey test", "explore the app and find errors/crashes", "collect screenshots of all screens", "smoke test the whole app", or asks for…
device-interaction
Verify iOS app behavior on device or simulator via screenshots, UI hierarchy, and touch interactions.
ax-testing
Skill "ax-testing" from Kasempiternal/axiom-v2, covering testing, quick patterns, swift testing basics, suites and traits and parameterized tests.
ios-simulator
Build, install, launch, inspect, and test iOS apps with Simulator and simctl. Use for simulator lifecycle, screenshots, logs, permissions, locations, push payloads, app containers, and repeatable local or CI verification.
swift-testing
Write, review, or migrate Swift unit tests using Swift Testing, while preserving XCTest/XCUITest where their APIs are still required. Use for test design, async behavior, traits, parameterization, migration boundaries, and version-gated testing APIs.
argent-test-ui-flow
Autonomously test an app UI (iOS or Android) by running interact-screenshot-verify loops using argent MCP tools. Use when testing UI flows, verifying login works, testing navigation, running end-to-end UI test scenarios, manual QA steps, visible UI changes, or visual behavior.